© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111388
    Prev
    Next
    INDEX
    Explanations

    root

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    forge
    -0.10
     Hampton
    -0.08
    alamat
    -0.08
     earm
    -0.08
    tabs
    -0.08
     Sisters
    -0.07
     recl
    -0.07
    .cookie
    -0.07
     reusable
    -0.07
     Forge
    -0.07
    POSITIVE LOGITS
     Root
    0.20
    -root
    0.20
    Root
    0.20
     root
    0.20
    ROOT
    0.19
     ROOT
    0.18
    /root
    0.18
     rooted
    0.18
    .Root
    0.18
     roots
    0.17
    Activations Density 0.306%

    No Known Activations